Abstract
AbstractAutomatically identifying thrombotic phenotypes based on clinical data, particularly clinical texts, can be challenging. Although many investigators have developed targeted information extraction methods for identifying thrombotic phenotypes from radiology notes, these methods can be time consuming to train, require large amounts of training data, and may miss subtle textual clues predictive of a thrombotic phenotype from notes beyond the radiology note. We developed a generalizable, data-driven framework for learning, characterizing, and visualizing clinical concepts from both radiology and discharge summaries predictive of thrombotic phenotypes.
Publisher
Cold Spring Harbor Laboratory
Reference26 articles.
1. Stroke Facts [Internet]. 2020 [cited 2021 Jan 18]. Available from: https://www.cdc.gov/stroke/facts.htm
2. CDC. Data and Statistics on Venous Thromboembolism [Internet]. 2020 [cited 2021 Jan 18]. Available from: https://www.cdc.gov/ncbddd/dvt/data.html
3. What is the incidence of myocardial infarction (MI, heart attack) in the US? [ Internet]. 2020 [cited 2021 Jan 18]. Available from: https://www.medscape.com/answers/155919-15093/what-is-the-incidence-of-myocardial-infarction-mi-heart-attack-in-the-us
4. Document-level classification of CT pulmonary angiography reports based on an extension of the ConText algorithm
5. Heilbrun ME , Chapman BE , Narasimhan E , Patel N , Mowery DL . Feasibility of natural language processing–assisted auditing of critical findings in chest radiology. Journal of the American College of Radiology. 2019;